alpha-research

/

AlphaResearch-RM-Qwen-7B

like 3

Follow

AlphaResearch 9

This PR enhances the model card for the AlphaResearch-RM-Qwen-7B model by adding essential metadata and updating the content for clarity and discoverability.

Key changes include:

• Added pipeline_tag: text-classification to correctly categorize this reward model, which performs binary classification of paper review scores.
• Added library_name: transformers as evidence from config.json and tokenizer_config.json indicates compatibility with the Hugging Face Transformers library, enabling the "How to use" widget.
• Linked to the official paper: AlphaResearch: Accelerating New Algorithm Discovery with Language Models.
• Included a link to the GitHub repository: https://github.com/answers111/alpha-research.
• Provided a detailed overview of the reward model's purpose, base model, training dataset, and evaluation metrics based on the GitHub README.
• Added the BibTeX citation.

These updates will improve model discoverability, provide users with crucial information, and ensure proper attribution.